Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Google developed Nano Banana 2, also known as Gemini 3.1 Flash Image Preview, to provide high-quality image generation and editing capabilities. This model processes both text and image inputs to produce visual or text outputs. It is designed to deliver professional-level visual results with fast processing speeds.
Nano Banana 2 (Gemini 3.1 Flash Image Preview) specs and pricing
- Provider: Google
- Released: February 26, 2026
- Context window: 66K tokens
- Max output: 59K tokens
- Input: images, text
- Output: images, text
- Price: $0.50 input / $3.00 output per 1M tokens
- Reasoning: yes
What Nano Banana 2 (Gemini 3.1 Flash Image Preview) is good at
- Generating high-quality images from text descriptions
- Editing existing visual content
- Multimodal tasks involving both text and image analysis
To-dos to try with Nano Banana 2 (Gemini 3.1 Flash Image Preview)
- Generate a high-resolution image based on a detailed text prompt
- Edit an uploaded image to change specific elements or styles
- Analyze an image and provide a descriptive text summary of its contents
FAQ
- What is the primary function of Nano Banana 2? It is a state-of-the-art model focused on image generation and image editing.
- Can this model process inputs other than text? Yes, the model is capable of accepting both image and text inputs.
- How much does Nano Banana 2 (Gemini 3.1 Flash Image Preview) cost? Nano Banana 2 (Gemini 3.1 Flash Image Preview) costs $0.50 per million input tokens and $3.00 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 1.82 credits ($1 = 100 credits).
- What is the context window of Nano Banana 2 (Gemini 3.1 Flash Image Preview)? Nano Banana 2 (Gemini 3.1 Flash Image Preview) can read up to 66K tokens at once and write up to 59K tokens in one reply.
- Can I use Nano Banana 2 (Gemini 3.1 Flash Image Preview) without coding? Yes. In todo.is you pick Nano Banana 2 (Gemini 3.1 Flash Image Preview) as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.